{"title":"Object Tracking Based on Global Context Attention","authors":"Yucheng Wang, Xi Chen, Zhongjie Mao, Jia Yan","doi":"10.4018/ijcini.287595","DOIUrl":null,"url":null,"abstract":"Previous research has shown that tracking algorithms cannot capture long-distance information and lead to the loss of the object when the object was deformed, the illumination changed, and the background was disturbed by similar objects. To remedy this, this article proposes an object-tracking method by introducing the Global Context attention module into the Multi-Domain Network (MDNet) tracker. This method can learn the robust feature representation of the object through the Global Context attention module to better distinguish the background from the object in the presence of interference factors. Extensive experiments on OTB2013, OTB2015, and UAV20L datasets show that the proposed method is significantly improved compared with MDNet and has competitive performance compared with more mainstream tracking algorithms. At the same time, the method proposed in this article achieves better results when the video sequence contains object deformation, illumination change, and background interference with similar objects.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"7 1","pages":"1-16"},"PeriodicalIF":0.6000,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Cognitive Informatics and Natural Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijcini.287595","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Previous research has shown that tracking algorithms cannot capture long-distance information and lead to the loss of the object when the object was deformed, the illumination changed, and the background was disturbed by similar objects. To remedy this, this article proposes an object-tracking method by introducing the Global Context attention module into the Multi-Domain Network (MDNet) tracker. This method can learn the robust feature representation of the object through the Global Context attention module to better distinguish the background from the object in the presence of interference factors. Extensive experiments on OTB2013, OTB2015, and UAV20L datasets show that the proposed method is significantly improved compared with MDNet and has competitive performance compared with more mainstream tracking algorithms. At the same time, the method proposed in this article achieves better results when the video sequence contains object deformation, illumination change, and background interference with similar objects.
期刊介绍:
The International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) encourages submissions that transcends disciplinary boundaries, and is devoted to rapid publication of high quality papers. The themes of IJCINI are natural intelligence, autonomic computing, and neuroinformatics. IJCINI is expected to provide the first forum and platform in the world for researchers, practitioners, and graduate students to investigate cognitive mechanisms and processes of human information processing, and to stimulate the transdisciplinary effort on cognitive informatics and natural intelligent research and engineering applications.